Skip to content

Security: LOSGARDIOS/codegraph

Security

SECURITY.md

Security Policy

Reporting a Vulnerability

Do NOT open a public issue for security vulnerabilities.

Email: security@agentskills.co.il

Response Timeline

  • Acknowledgment: Within 24 hours
  • Initial assessment: Within 72 hours
  • Resolution target: Based on severity

What to Include

  • Description of the vulnerability
  • Steps to reproduce
  • Which skill(s) are affected
  • Potential impact

Security Scanning Pipeline

Every skill submission goes through automated security scanning:

  1. SKILL.md Validation - Checks for hardcoded secrets (API keys, tokens, passwords)
  2. Snyk Agent Scan (mcp-scan) - Detects prompt injection, data exfiltration, credential theft, obfuscated payloads using LLM-based intent analysis
  3. Dependency Scan - If the skill includes package.json or requirements.txt, dependencies are scanned with --severity-threshold=high

Scope

This policy covers all repositories under the skills-il GitHub organization.

Responsible Disclosure

We follow responsible disclosure practices. We will:

  • Confirm receipt of your report
  • Keep you informed of progress
  • Credit you in the fix (unless you prefer anonymity)
  • Not take legal action against good-faith researchers

There aren't any published security advisories